Deep learning-based malignancy probability estimation of pulmonary nodules in PET/CT imaging
European Radiology · 11.07.2026
DOI: 10.1007/s00330-026-12744-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Radiology, online erschienen am 11.07.2026. Verfasst von Lars Leijten und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands. lars.leijten@radboudumc.nl. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovative Health Initiative.
Abstract (Originalsprache)
Objective
The current BTS guidelines recommend evaluation of suspicious pulmonary nodules using [ 18 F]FDG-PET/CT imaging, followed by Herder model risk stratification. However, it is based on limited imaging features, which may limit diagnostic accuracy. This study aims to develop a PET/CT-based deep learning (DL) model for malignancy probability estimation (AITO-PETCT-MP) and compare its performance to the Herder model and clinician performance. Materials and methods In a single-center retrospective study, we collected 533 indeterminate pulmonary nodules (268 malignant) with a mean diameter of 18.4 mm (SD ± 12.1) in 436 patients. Histopathological malignancy confirmation or a minimum 2-year benign national cancer registry follow-up served as the reference standard. Model diagnostic performance was compared against the Herder model and seven clinicians in a reader study on a test set of 161 nodules (80 malignant).
Results
AITO-PETCT-MP achieved an AUC of 0.78 [95% CI: 0.70–0.85] compared to the Herder model: AUC = 0.73 [0.65–0.80] (non-inferiority: p = 0.005). On average, experienced clinicians achieved an AUC of 0.80 [0.75–0.85]. Stratifying into BTS follow-up categories, the Herder model referred more benign nodules for potential direct treatment (26/81) than AITO-PETCT-MP and clinicians (both 3/81), while AITO-PETCT-MP and clinicians assigned more malignant cases to CT surveillance instead of direct treatment.
Conclusion
AITO-PETCT-MP demonstrated non-inferior performance to the guideline-recommended Herder model, while only using imaging data. Diagnostic performance fell in the performance range of seven clinicians. Differences in BTS follow-up recommendations between the Herder model and clinicians suggest a difference in patient management compared to current clinical practice. Key Points Question How well can an imaging-only deep learning model estimate pulmonary nodule malignancy probability on [ 18 F]FDG-PET/CT compared to the established Herder model and expert clinicians?
Findings
The model (AITO-PETCT-MP) performed non-inferior to the Herder model (AUC 0.78 vs 0.73, p = 0.005) and comparably to seven expert readers (AUC 0.74–0.87). Clinical relevance BTS-based follow-up stratification showed the Herder model referred more benign nodules to potential direct treatment than clinicians and AITO-PETCT-MP, while assigning fewer malignant cases to surveillance. This suggests a difference between Herder recommendations and current clinical practice.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands. lars.leijten@radboudumc.nl.
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands.
- Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
- Department of Pulmonary Diseases, Radboud University Medical Center, Nijmegen, The Netherlands.
- Department of Radiology and Nuclear Medicine, Ziekenhuis Gelderse Vallei, Ede, The Netherlands.
Förderung
- Innovative Health Initiative
Zitieren
APA
Leijten, L., Aarntzen, E. H. J. G., Verhoeven, R. L. J., Brouwers, A. H., Geurts, B., van der Heide, J. A., Koopmans, K. P., Noordzij, W., Stormezand, G. N., van der Heijden, E. H. F. M., & Jacobs, C. (2026). Deep learning-based malignancy probability estimation of pulmonary nodules in PET/CT imaging. European Radiology. https://doi.org/10.1007/s00330-026-12744-9
Vancouver
Leijten L, Aarntzen EHJG, Verhoeven RLJ, Brouwers AH, Geurts B, van der Heide JA, et al. Deep learning-based malignancy probability estimation of pulmonary nodules in PET/CT imaging. European Radiology. 2026. doi:10.1007/s00330-026-12744-9
BibTeX
@article{Leijten2026,
author = {Leijten, Lars and Aarntzen, Erik H J G and Verhoeven, Roel L J and Brouwers, Adrienne H and Geurts, Bram and van der Heide, Johannes A and Koopmans, Klaas Pieter and Noordzij, Walter and Stormezand, Gilles N and van der Heijden, Erik H F M and Jacobs, Colin},
title = {Deep learning-based malignancy probability estimation of pulmonary nodules in PET/CT imaging},
journal = {European Radiology},
year = {2026},
doi = {10.1007/s00330-026-12744-9}
}
EUVIMED